Loading...
Loading...
Found 9,634 Skills
Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.
Verify your own completed code changes using the repo's existing infrastructure and an independent evaluator context. Use after implementing a change when you need to run unit or integration tests, check build or lint gates, prove the real surface works with evidence, and challenge the changed code for clarity, deduplication, and maintainability. If the repo is not verifiable yet, hand off to `agent-readiness`; if you are reviewing someone else's code, use `review`.
Used when executing implementation plans with independent tasks in the current session
Run a structured multi-perspective council on a hard decision, design choice, debugging question, strategy problem, or tradeoff. Use when the user wants multiple viewpoints, explicit cross-examination, and a compact final verdict.
Refactor code with safety nets — tests green before and after, no behavior change
Manage Linear tickets, projects, milestones, and documents. Use for coordinating work across skills (orca-security, multi-repo) or tracking remediation progress.
Guide a CS or AI PhD student through a focused literature review sprint that produces a ranked paper map, notes, gaps, and next actions. Use this skill whenever the user needs to survey a topic, prepare related work, check whether an idea is novel, catch up on a field, read papers before a meeting, or turn a pile of papers into an organized research direction.
Use when a complex MEL/SRHR task requires deep evidence synthesis before planning begins. Triggered by Ann between PHASE 1 and PHASE 2 for COMPLEX tasks, or directly by Ane for standalone literature reviews.
Persistent project-scoped store for deep research on large topics. Use for substantive questions - comparing libraries, evaluating tools, surveying solutions to hard problems. Not for plan notes, not for small facts, not for code-level decisions, not for ideas.
Display the current state of the FPF knowledge base
Create pull requests using GitHub CLI with proper templates and formatting
Analyze command history to identify which skills work, which fail, and where to improve.